Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add KevinZai/commander --skill auth-packgit clone --depth 1 https://github.com/KevinZai/commanderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kevinzai/commander/auth-pack)<a href="https://agentmods.dev/skills/kevinzai/commander/auth-pack"><img src="https://agentmods.dev/badge/skills/kevinzai/commander/auth-pack.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00020 | $0.00532 |
| Opus 5 | $0.00010 | $0.00266 |
| Sonnet 5 | $0.00004 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
ccc-pro-auth scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
What this pack will do
- Scaffold SAML 2.0 SP metadata and assertion consumer service handlers
- Wire OIDC Authorization Code flow with PKCE (RFC 7636 compliant)
- Generate Okta integration: app registration, attribute mapping, group sync
- Generate Auth0 integration: tenant config, rules/actions, M2M credentials
- Generate Azure AD / Entra ID integration: app registration, manifest, MSAL config
- Scaffold JIT (just-in-time) user provisioning with conflict resolution
- Add MFA enforcement at the middleware layer (TOTP + WebAuthn)
- Generate role-based access control schema + middleware stubs (RBAC)
- Add session security hardening: rotation, sliding windows, device fingerprinting
- Scaffold SSO test suite: happy path, expired assertion, replayed token, IdP-initiated
- Generate identity provider migration runbook (Okta → Auth0, Auth0 → Cognito, etc.)
- Add passwordless flows: magic link + passkey (WebAuthn Level 2)
- Scaffold OAuth 2.0 client credentials flow for M2M / service accounts
- Wire logout: SLO (Single Logout) for SAML, end_session for OIDC
Why Pro-only
Enterprise identity patterns require deep, opinionated scaffolding against 6+ IdP vendor APIs — each with its own quirks, SDK versions, and compliance gotchas. The curation and testing burden is high. This pack will save 2–4 weeks of integration work per project.
Coming in v4.2
This skill is scaffolded. Full implementation ships in v4.2. Sign up at commanderplugin.com/pro to get notified and receive early access.
Tier check
This skill checks isPro() from commander/cowork-plugin/lib/license.js before running. If your license tier is starter, it surfaces an upgrade prompt and exits cleanly — no partial scaffolding, no silent failure.
Reference
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 48 lines · 20 tokens per session scan A aa00c90b1c41
ccc-pro-auth is a skill published in the GitHub repository KevinZai/commander (6 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 532 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
mcp-server-dev
Create MCP servers — multi-tool services exposed via Model Context Protocol. Use this skill whenever users mention MCP servers, building servers, server scaffolding, tool registration, or want to package tools for distribution via uvx or npx. Also use when the conversation involves stdio transport, server lifecycle…
mcp-tool-dev
Create MCP tools — individual tool functions exposed via Model Context Protocol. Use this skill whenever users mention MCP tools, tool handlers, tool functions, tool definitions, or want to add capabilities to an MCP server. Also use when the conversation involves designing tool schemas, writing tool descriptions, or…
email-systems
Transactional email (Resend, SendGrid, SES), templates (React Email, MJML), deliverability (SPF/DKIM/DMARC), and inboxing best practices. Use when building email infrastructure, designing templates, or troubleshooting deliverability.
symfony:config-env-parameters
Manage Symfony configuration with .env files, parameters, secrets vault, and environment-specific settings.
symfony:messenger-retry-failures
Handle message failures with retry strategies, failure transport, and recovery in Symfony Messenger (Recoverable/Unrecoverable exceptions).
multi-plan-handoff
Auto-detect plan files in conversation context and pass them to multi: execute subagents by reference, not by paraphrase.